Transformer Scale Gate for Semantic Segmentation

05/14/2022
by   Hengcan Shi, et al.
0

Effectively encoding multi-scale contextual information is crucial for accurate semantic segmentation. Existing transformer-based segmentation models combine features across scales without any selection, where features on sub-optimal scales may degrade segmentation outcomes. Leveraging from the inherent properties of Vision Transformers, we propose a simple yet effective module, Transformer Scale Gate (TSG), to optimally combine multi-scale features.TSG exploits cues in self and cross attentions in Vision Transformers for the scale selection. TSG is a highly flexible plug-and-play module, and can easily be incorporated with any encoder-decoder-based hierarchical vision Transformer architecture. Extensive experiments on the Pascal Context and ADE20K datasets demonstrate that our feature selection strategy achieves consistent gains.

READ FULL TEXT

page 1

page 3

page 4

page 6

page 7

page 8

page 16

page 17

research
03/26/2022

Feature Selective Transformer for Semantic Image Segmentation

Recently, it has attracted more and more attentions to fuse multi-scale ...
research
05/02/2023

Exploring vision transformer layer choosing for semantic segmentation

Extensive work has demonstrated the effectiveness of Vision Transformers...
research
10/10/2022

LAPFormer: A Light and Accurate Polyp Segmentation Transformer

Polyp segmentation is still known as a difficult problem due to the larg...
research
05/31/2022

ViT-BEVSeg: A Hierarchical Transformer Network for Monocular Birds-Eye-View Segmentation

Generating a detailed near-field perceptual model of the environment is ...
research
06/25/2022

CV 3315 Is All You Need : Semantic Segmentation Competition

This competition focus on Urban-Sense Segmentation based on the vehicle ...
research
04/07/2023

A Cross-Scale Hierarchical Transformer with Correspondence-Augmented Attention for inferring Bird's-Eye-View Semantic Segmentation

As bird's-eye-view (BEV) semantic segmentation is simple-to-visualize an...
research
05/31/2021

SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers

We present SegFormer, a simple, efficient yet powerful semantic segmenta...

Please sign up or login with your details

Forgot password? Click here to reset